Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ > Class Template Reference

A Metropolis-Hastings Random Walk. More...

#include <tomographer/mhrw.h>

Inheritance diagram for Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >:

Collaboration diagram for Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >:

Public Types
enum
typedef Rng_	Rng
	Random number generator type (see C++ std::random)
typedef MHWalker_	MHWalker
	The random walker type which knows about the state space and jump function.
typedef MHRWStatsCollector_	MHRWStatsCollector
	The stats collector type (see MHRWStatsCollector Interface)
typedef LoggerType_	LoggerType
	The logger type which will be provided by user to constructor (see Logging and Loggers)
typedef CountIntType_	CountIntType
	The type used for counting numbers of iterations (see, e.g. nSweep() or MHRWParams)
typedef MHWalker::PointType	PointType
	The type of a point in the random walk.
typedef MHWalker::StepRealType	StepRealType
	The type of a step size of the random walk.
typedef MHRWParams< CountIntType, StepRealType >	MHRWParamsType
	The struct which can hold the parameters of this random walk.
typedef _FnValueType	FnValueType
	The type of the Metropolis-Hastings function value. (See class documentation)

Public Member Functions
	MHRandomWalk (StepRealType step_size, CountIntType n_sweep, CountIntType n_therm, CountIntType n_run, MHWalker &mhwalker, MHRWStatsCollector &stats, Rng &rng, LoggerType &logger_)
	Simple constructor, initializes the given fields.
template<typename MHRWParamsType >
	MHRandomWalk (MHRWParamsType &&n_rw, MHWalker &mhwalker, MHRWStatsCollector &stats, Rng &rng, LoggerType &logger_)
	Simple constructor, initializes the given fields.
	MHRandomWalk (const MHRandomWalk &other)=delete
MHRWParamsType	mhrwParams () const
	The parameters of the random walk.
StepRealType	stepSize () const
	Get the step size of the random walk.
CountIntType	nSweep () const
	Number of iterations in a sweep.
CountIntType	nTherm () const
	Number of thermalizing sweeps.
CountIntType	nRun () const
	Number of live run sweeps.
bool	hasAcceptanceRatio () const
	Query whether we have any statistics about acceptance ratio. This is false, for example, during the thermalizing runs.
template<typename RatioType = double>
RatioType	acceptanceRatio () const
	Return the acceptance ratio so far.
const PointType &	getCurrentPoint () const
	Access the current state of the random walk. More...
const FnValueType &	getCurrentPointValue () const
	Access the current function value of the random walk. More...
void	setCurrentPoint (const PointType &pt)
	Force manual state of random walk. More...
void	run ()
	Run the random walk. (pun intended) More...

Detailed Description

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>
class Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >

A Metropolis-Hastings Random Walk.

Implements a Metropolis-Hastings random walk. This takes care of accepting or rejecting a new point and taking samples.

This class takes care to update the state of a random walk for it to perform thermalizing sweeps, followed by "live" runs.

The random walk is composed of iterations. There are n_sweep iterations per "sweep". This number should be approximately chosen such that step_size * n_sweep is of order of the size of the state space. (This is in order to better decorrelate the samples.)

Initially, a number n_therm of thermalizing sweeps are performed. No samples are taken during this period, and this is meant for a Metropolis random walk to find its "valley".

After the thermalizing runs, a number of run sweeps are performed, in which a live sample is taken at the last iteration of each sweep.

Template Parameters

Rng	is a C++ random number generator (for example, std::mt19937)
MHWalker	is responsible for dealing with the state space, providing a new proposal point and calculating the function value at different points. See MHWalker Interface.
MHRWStatsCollector	takes care of collecting useful data during a random walk. It should be a type implementing a MHRWStatsCollector interface, see MHRWStatsCollector Interface.
LoggerType	is a logger type to which log messages can be generated (see Logging and Loggers)
CountIntType	is an integer type used to count the number of iterations. You'll want to use int here, unless you really want to pursue exceptionally long random walks.

Definition at line 290 of file mhrw.h.

Member Enumeration Documentation

anonymous enum

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>

anonymous enum

Enumerator
UseFnSyntaxType	How to calculate the Metropolis-Hastings jump probability ratio (see class documentation)

Definition at line 322 of file mhrw.h.

Member Function Documentation

getCurrentPoint()

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>

const PointType& Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >::getCurrentPoint ( ) const

inline

Access the current state of the random walk.

Returns

the current point the random walk is located at.

Definition at line 429 of file mhrw.h.

getCurrentPointValue()

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>

const FnValueType& Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >::getCurrentPointValue ( ) const

inline

Access the current function value of the random walk.

Returns

the current value of the function in the current state of the random walk.

Warning

the meaning of this value depends on MHRandomWalk::UseFnSyntaxType. It is either the value of the function, its logarithm, or a dummy value.

Definition at line 441 of file mhrw.h.

run()

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>

void Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >::run ( )

inline

Run the random walk. (pun intended)

This will take care of the full random walk. The specified number of thermalizing sweeps will be run, followed by a number of "live" sweeps where one sample is taken per sweep.

Definition at line 569 of file mhrw.h.

setCurrentPoint()

template<typename Rng_, typename MHWalker_, typename MHRWStatsCollector_, typename LoggerType_, typename CountIntType_ = int>

void Tomographer::MHRandomWalk< Rng_, MHWalker_, MHRWStatsCollector_, LoggerType_, CountIntType_ >::setCurrentPoint ( const PointType &  pt )

inline

Force manual state of random walk.

This may be called to force setting the current state of the random walk to the given point pt.

Definition at line 451 of file mhrw.h.

---

The documentation for this class was generated from the following file:

• tomographer/mhrw.h (v4.1)